Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn how to implement voice control in React.js applications using TensorFlow.js in this 28-minute tutorial. Discover how to leverage AI-powered speech command recognition to control on-screen elements using only a browser and microphone. Follow along as the instructor demonstrates accessing a pre-built speech command recognition app, building real-time voice-controlled interactions, and rendering canvas visualizations based on detected AI speech commands. Gain hands-on experience in cloning the pre-built app, installing dependencies, setting up visualization functions, creating canvases, defining references and states, handling speech command actions, and testing the AI speech command recognition. By the end of this tutorial, you'll be able to create interactive web applications that respond to voice commands, enhancing user experience and accessibility.
Syllabus
- Start
- Cloning the Pre-Build Speech Command Recognition App
- Installing Baseline Dependencies
- Setting Up a Visualisation Function
- Creating a Canvas
- Defining Canvas References and Application States
- Setting up Speech Command Action Handling
- Testing Out AI Speech Command Recognition
- Handling Consecutive Commands
- Final Code Test
Taught by
Nicholas Renotte